1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
|
import re
from .common import InfoExtractor
from ..utils import (
parse_duration,
traverse_obj,
unescapeHTML,
unified_timestamp,
urljoin
)
class NhkBaseIE(InfoExtractor):
_API_URL_TEMPLATE = 'https://nwapi.nhk.jp/nhkworld/%sod%slist/v7b/%s/%s/%s/all%s.json'
_BASE_URL_REGEX = r'https?://www3\.nhk\.or\.jp/nhkworld/(?P<lang>[a-z]{2})/ondemand'
_TYPE_REGEX = r'/(?P<type>video|audio)/'
def _call_api(self, m_id, lang, is_video, is_episode, is_clip):
return self._download_json(
self._API_URL_TEMPLATE % (
'v' if is_video else 'r',
'clip' if is_clip else 'esd',
'episode' if is_episode else 'program',
m_id, lang, '/all' if is_video else ''),
m_id, query={'apikey': 'EJfK8jdS57GqlupFgAfAAwr573q01y6k'})['data']['episodes'] or []
def _extract_episode_info(self, url, episode=None):
fetch_episode = episode is None
lang, m_type, episode_id = NhkVodIE._match_valid_url(url).groups()
if len(episode_id) == 7:
episode_id = episode_id[:4] + '-' + episode_id[4:]
is_video = m_type == 'video'
if fetch_episode:
episode = self._call_api(
episode_id, lang, is_video, True, episode_id[:4] == '9999')[0]
title = episode.get('sub_title_clean') or episode['sub_title']
def get_clean_field(key):
return episode.get(key + '_clean') or episode.get(key)
series = get_clean_field('title')
thumbnails = []
for s, w, h in [('', 640, 360), ('_l', 1280, 720)]:
img_path = episode.get('image' + s)
if not img_path:
continue
thumbnails.append({
'id': '%dp' % h,
'height': h,
'width': w,
'url': 'https://www3.nhk.or.jp' + img_path,
})
info = {
'id': episode_id + '-' + lang,
'title': '%s - %s' % (series, title) if series and title else title,
'description': get_clean_field('description'),
'thumbnails': thumbnails,
'series': series,
'episode': title,
}
if is_video:
vod_id = episode['vod_id']
info.update({
'_type': 'url_transparent',
'ie_key': 'Piksel',
'url': 'https://player.piksel.com/v/refid/nhkworld/prefid/' + vod_id,
'id': vod_id,
})
else:
if fetch_episode:
audio_path = episode['audio']['audio']
info['formats'] = self._extract_m3u8_formats(
'https://nhkworld-vh.akamaihd.net/i%s/master.m3u8' % audio_path,
episode_id, 'm4a', entry_protocol='m3u8_native',
m3u8_id='hls', fatal=False)
for f in info['formats']:
f['language'] = lang
else:
info.update({
'_type': 'url_transparent',
'ie_key': NhkVodIE.ie_key(),
'url': url,
})
return info
class NhkVodIE(NhkBaseIE):
# the 7-character IDs can have alphabetic chars too: assume [a-z] rather than just [a-f], eg
_VALID_URL = r'%s%s(?P<id>[0-9a-z]{7}|[^/]+?-\d{8}-[0-9a-z]+)' % (NhkBaseIE._BASE_URL_REGEX, NhkBaseIE._TYPE_REGEX)
# Content available only for a limited period of time. Visit
# https://www3.nhk.or.jp/nhkworld/en/ondemand/ for working samples.
_TESTS = [{
# video clip
'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/video/9999011/',
'md5': '7a90abcfe610ec22a6bfe15bd46b30ca',
'info_dict': {
'id': 'a95j5iza',
'ext': 'mp4',
'title': "Dining with the Chef - Chef Saito's Family recipe: MENCHI-KATSU",
'description': 'md5:5aee4a9f9d81c26281862382103b0ea5',
'timestamp': 1565965194,
'upload_date': '20190816',
},
}, {
# audio clip
'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/audio/r_inventions-20201104-1/',
'info_dict': {
'id': 'r_inventions-20201104-1-en',
'ext': 'm4a',
'title': "Japan's Top Inventions - Miniature Video Cameras",
'description': 'md5:07ea722bdbbb4936fdd360b6a480c25b',
},
'params': {
# m3u8 download
'skip_download': True,
},
}, {
'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/video/2015173/',
'only_matching': True,
}, {
'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/audio/plugin-20190404-1/',
'only_matching': True,
}, {
'url': 'https://www3.nhk.or.jp/nhkworld/fr/ondemand/audio/plugin-20190404-1/',
'only_matching': True,
}, {
'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/audio/j_art-20150903-1/',
'only_matching': True,
}, {
# video, alphabetic character in ID #29670
'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/video/9999a34/',
'only_matching': True,
'info_dict': {
'id': 'qfjay6cg',
'ext': 'mp4',
'title': 'DESIGN TALKS plus - Fishermen’s Finery',
'description': 'md5:8a8f958aaafb0d7cb59d38de53f1e448',
'thumbnail': r're:^https?:/(/[a-z0-9.-]+)+\.jpg\?w=1920&h=1080$',
'upload_date': '20210615',
'timestamp': 1623722008,
}
}]
def _real_extract(self, url):
return self._extract_episode_info(url)
class NhkVodProgramIE(NhkBaseIE):
_VALID_URL = r'%s/program%s(?P<id>[0-9a-z]+)(?:.+?\btype=(?P<episode_type>clip|(?:radio|tv)Episode))?' % (NhkBaseIE._BASE_URL_REGEX, NhkBaseIE._TYPE_REGEX)
_TESTS = [{
# video program episodes
'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/program/video/japanrailway',
'info_dict': {
'id': 'japanrailway',
'title': 'Japan Railway Journal',
},
'playlist_mincount': 1,
}, {
# video program clips
'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/program/video/japanrailway/?type=clip',
'info_dict': {
'id': 'japanrailway',
'title': 'Japan Railway Journal',
},
'playlist_mincount': 5,
}, {
'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/program/video/10yearshayaomiyazaki/',
'only_matching': True,
}, {
# audio program
'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/program/audio/listener/',
'only_matching': True,
}]
def _real_extract(self, url):
lang, m_type, program_id, episode_type = self._match_valid_url(url).groups()
episodes = self._call_api(
program_id, lang, m_type == 'video', False, episode_type == 'clip')
entries = []
for episode in episodes:
episode_path = episode.get('url')
if not episode_path:
continue
entries.append(self._extract_episode_info(
urljoin(url, episode_path), episode))
program_title = None
if entries:
program_title = entries[0].get('series')
return self.playlist_result(entries, program_id, program_title)
class NhkForSchoolBangumiIE(InfoExtractor):
_VALID_URL = r'https?://www2\.nhk\.or\.jp/school/movie/(?P<type>bangumi|clip)\.cgi\?das_id=(?P<id>[a-zA-Z0-9_-]+)'
_TESTS = [{
'url': 'https://www2.nhk.or.jp/school/movie/bangumi.cgi?das_id=D0005150191_00000',
'info_dict': {
'id': 'D0005150191_00003',
'title': 'にている かな',
'duration': 599.999,
'timestamp': 1396414800,
'upload_date': '20140402',
'ext': 'mp4',
'chapters': 'count:12'
},
'params': {
# m3u8 download
'skip_download': True,
},
}]
def _real_extract(self, url):
program_type, video_id = self._match_valid_url(url).groups()
webpage = self._download_webpage(
f'https://www2.nhk.or.jp/school/movie/{program_type}.cgi?das_id={video_id}', video_id)
# searches all variables
base_values = {g.group(1): g.group(2) for g in re.finditer(r'var\s+([a-zA-Z_]+)\s*=\s*"([^"]+?)";', webpage)}
# and programObj values too
program_values = {g.group(1): g.group(3) for g in re.finditer(r'(?:program|clip)Obj\.([a-zA-Z_]+)\s*=\s*(["\'])([^"]+?)\2;', webpage)}
# extract all chapters
chapter_durations = [parse_duration(g.group(1)) for g in re.finditer(r'chapterTime\.push\(\'([0-9:]+?)\'\);', webpage)]
chapter_titles = [' '.join([g.group(1) or '', unescapeHTML(g.group(2))]).strip() for g in re.finditer(r'<div class="cpTitle"><span>(scene\s*\d+)?</span>([^<]+?)</div>', webpage)]
# this is how player_core.js is actually doing (!)
version = base_values.get('r_version') or program_values.get('version')
if version:
video_id = f'{video_id.split("_")[0]}_{version}'
formats = self._extract_m3u8_formats(
f'https://nhks-vh.akamaihd.net/i/das/{video_id[0:8]}/{video_id}_V_000.f4v/master.m3u8',
video_id, ext='mp4', m3u8_id='hls')
duration = parse_duration(base_values.get('r_duration'))
chapters = None
if chapter_durations and chapter_titles and len(chapter_durations) == len(chapter_titles):
start_time = chapter_durations
end_time = chapter_durations[1:] + [duration]
chapters = [{
'start_time': s,
'end_time': e,
'title': t,
} for s, e, t in zip(start_time, end_time, chapter_titles)]
return {
'id': video_id,
'title': program_values.get('name'),
'duration': parse_duration(base_values.get('r_duration')),
'timestamp': unified_timestamp(base_values['r_upload']),
'formats': formats,
'chapters': chapters,
}
class NhkForSchoolSubjectIE(InfoExtractor):
IE_DESC = 'Portal page for each school subjects, like Japanese (kokugo, 国語) or math (sansuu/suugaku or 算数・数学)'
KNOWN_SUBJECTS = (
'rika', 'syakai', 'kokugo',
'sansuu', 'seikatsu', 'doutoku',
'ongaku', 'taiiku', 'zukou',
'gijutsu', 'katei', 'sougou',
'eigo', 'tokkatsu',
'tokushi', 'sonota',
)
_VALID_URL = r'https?://www\.nhk\.or\.jp/school/(?P<id>%s)/?(?:[\?#].*)?$' % '|'.join(re.escape(s) for s in KNOWN_SUBJECTS)
_TESTS = [{
'url': 'https://www.nhk.or.jp/school/sougou/',
'info_dict': {
'id': 'sougou',
'title': '総合的な学習の時間',
},
'playlist_mincount': 16,
}, {
'url': 'https://www.nhk.or.jp/school/rika/',
'info_dict': {
'id': 'rika',
'title': '理科',
},
'playlist_mincount': 15,
}]
def _real_extract(self, url):
subject_id = self._match_id(url)
webpage = self._download_webpage(url, subject_id)
return self.playlist_from_matches(
re.finditer(rf'href="((?:https?://www\.nhk\.or\.jp)?/school/{re.escape(subject_id)}/[^/]+/)"', webpage),
subject_id,
self._html_search_regex(r'(?s)<span\s+class="subjectName">\s*<img\s*[^<]+>\s*([^<]+?)</span>', webpage, 'title', fatal=False),
lambda g: urljoin(url, g.group(1)))
class NhkForSchoolProgramListIE(InfoExtractor):
_VALID_URL = r'https?://www\.nhk\.or\.jp/school/(?P<id>(?:%s)/[a-zA-Z0-9_-]+)' % (
'|'.join(re.escape(s) for s in NhkForSchoolSubjectIE.KNOWN_SUBJECTS)
)
_TESTS = [{
'url': 'https://www.nhk.or.jp/school/sougou/q/',
'info_dict': {
'id': 'sougou/q',
'title': 'Ｑ～こどものための哲学',
},
'playlist_mincount': 20,
}]
def _real_extract(self, url):
program_id = self._match_id(url)
webpage = self._download_webpage(f'https://www.nhk.or.jp/school/{program_id}/', program_id)
title = (self._generic_title('', webpage)
or self._html_search_regex(r'<h3>([^<]+?)とは？\s*</h3>', webpage, 'title', fatal=False))
title = re.sub(r'\s*\|\s*NHK\s+for\s+School\s*$', '', title) if title else None
description = self._html_search_regex(
r'(?s)<div\s+class="programDetail\s*">\s*<p>[^<]+</p>',
webpage, 'description', fatal=False, group=0)
bangumi_list = self._download_json(
f'https://www.nhk.or.jp/school/{program_id}/meta/program.json', program_id)
# they're always bangumi
bangumis = [
self.url_result(f'https://www2.nhk.or.jp/school/movie/bangumi.cgi?das_id={x}')
for x in traverse_obj(bangumi_list, ('part', ..., 'part-video-dasid')) or []]
return self.playlist_result(bangumis, program_id, title, description)
|
